We present a novel, real-time, semantic segmentation network in which the
encoder both encodes and generates the parameters (weights) of the decoder.
Furthermore, to allow maximal adaptivity, the weights at each decoder block
vary spatially. For this purpose, we design a new type of hypernetwork,
composed of a nested U-Net for drawing higher level context features, a
multi-headed weight generating module which generates the weights of each block
in the decoder immediately before they are consumed, for efficient memory
utilization, and a primary network that is composed of novel dynamic patch-wise
convolutions. Despite the usage of less-conventional blocks, our architecture
obtains real-time performance. In terms of the runtime vs. accuracy trade-off,
we surpass state of the art (SotA) results on popular semantic segmentation
benchmarks: PASCAL VOC 2012 (val. set) and real-time semantic segmentation on
Cityscapes, and CamVid. The code is available: this https URL

本文提出了一种新颖的实时语义分割神经网络，其中编码器既编码也生成解码器的参数 (权重)，并且为了实现最大的适应性，每个解码器块的权重都在空间上有所变化。我们设计了一种新型的超网络，在其中，用于绘制高级上下文特征的嵌套 U-Net、多头权重生成模块，该模块在解码器使用权重之前立即生成解码器每个块的权重，以实现高效的内存利用，以及由新颖的动态面向补丁的卷积组成的主要网络。尽管使用了较不常见的块，但我们的架构实现了实时性能，在运行时间与准确性的权衡方面，在流行的语义分割基准测试上 (PASCAL VOC 2012, Cityscapes 和 CamVid) 的表现都超过了最先进的结果。